INDEX

Explanations

references to the term "Ace."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

acetabular prefixes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.45

 ISNI

-0.40

 sanitarias

-0.40

-------------</

-0.38

➯

-0.38

 Curitiba

-0.37

щенный

-0.36

 Detalles

-0.35

neath

-0.35

Gemeinden

-0.35

POSITIVE LOGITS

Ace

0.90

Ace

0.88

ace

0.74

ACE

0.73

ace

0.71

demic

0.65

bootstrapcdn

0.65

taminophen

0.62

 Aces

0.60

 aceto

0.58

Activations Density 0.006%

references to the term "Ace."

acetabular prefixes

No Comments

No Known Activations